Simple Regression Analysis Hypothesis Test

40 criterion not happen heterokedasticity if the significance value 0,05. Conversely, if the significance value 0,05 was happen heterokedasticity between independent variables. Ghazali, 2011: 142.

3. Hypothesis Test

a. Simple Regression Analysis

The analysis technique is to test the effect of the independent variables with the dependent variable, which is to determine the effect of Teacher Profession Perception toward Accounting Teacher Interest hypothesis 1, the effect of Family Environment toward Accounting Teacher Interest hypothesis 2. The Steps must be taken in a simple regression analysis as follows: 1. Finding correlation coefficient between XI and Y, X2 and Y. The formula is: � = ∑ √∑ ∑ Descriptions: r xy = coefficient correlation between X1 and X2 with Y x = Teacher Profession Perception Family Environment y = Accounting Teacher Interest ∑xy = Total between X and Y ∑x 2 = Square total of X score ∑y 2 = Square total of Y score Sutrisno Hadi, 2004: 4 The correlation of direction will be positive if the result of calculation of correlation is at least the plus +. If the minus sign is -, it will be toward a negative. 41 2. Finding a determination coefficient The coefficient of determination is the level of the effect of independent variables X1 and X2 on the dependent variable Y. The formula used as follows: r 2 = r 2 Description: r 2 = determination coefficient r = correlation coefficient The effects of independent variables X1 and X2 are on the dependent variable Y by the square of the correlation coefficient. Furthermore, the coefficient of determination multiplied by 100 to determine the level of the effect of independent variables on the dependent variable in terms of percentage. 3. Make a simply line regression Y = aX + K Formula: Descriptions : Y = Accounting Teacher Interest a = Coefficient number X = Student’s Perception of Teacher ProfessionFamily Environment K = Constant number Sutrisno Hadi, 2004: 1 4. Examine coefficient correlation with t test T test used to examine significant between variable. The formula used as follows: 42 � = �√ − √ − �² Descriptions: t = t count r = correlation coefficient n = total of respondents r 2 = square of correlation coefficient Sugiyono, 2012: 230 The conclusion is to compare tcount with ttable. If tcount greater than or equal to the level ttable significant 5 than these variables significantly affect the independent variable. Conversely, if tcount smaller than ttable the effect of the variable is not significant.

b. Multiple Regression Analysis